© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6359
    Prev
    Next
    INDEX
    Explanations

    how much

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on numeric tokens containing decimal points (floating‐point numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bells
    0.59
    她是
    0.58
    她在
    0.55
     dugg
    0.55
     ETF
    0.54
    ceğine
    0.53
     Pigeon
    0.53
    /
    0.53
     elle
    0.53
     ella
    0.52
    POSITIVE LOGITS
     mengubah
    0.68
    ̟
    0.66
     succumb
    0.63
     تمہ
    0.62
    тус
    0.61
    Penumpang
    0.59
    ья
    0.59
    বর্ধমান
    0.59
     руко
    0.58
     เปลี่ยน
    0.57
    Activations Density 0.000%

    No Known Activations